User Tools

Site Tools


syllabus

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision
Previous revision
syllabus [2016/05/04 11:06]
anderson [Grading]
syllabus [2020/12/06 10:37] (current)
anderson [Grading]
Line 3: Line 3:
 ===== Description ===== ===== Description =====
  
-This course covers fundamental concepts and methods of computational data analysis, including pattern classification, prediction, visualization, and recent topics in deep learningStudents will learn how to+The course objectives are to learn the fundamental theories, 
 +algorithms and concepts in Artificial 
 +Intelligence Class discussions will range from algorithm 
 +fundamentals to philosophical issues in Artificial 
 +Intelligence. Programs implementing problem-solving search, logical 
 +reasoning. and machine learning techniques will be studied and 
 +modified. Other topics will be covered as time permits.  Students must 
 +complete a number of programming assignments and a 
 +semester project.
  
-  * read data files of various formats and visualize characteristics of the data, +We will be using [[https://www.python.org/|Python]] for assignment 
-  * perform statistical analyses on multivariate data, +solutions. Previous experience with Python 
-  * develop and apply pattern classification algorithms to classify multivariate data, +and its numpy package is helpful.  To prepare for this courseplease 
-  * develop and apply regression algorithms for finding relationships between data variables+download and install Python on your computerand work through on-line 
-  * develop and apply reinforcement learning algorithms for learning to control complex systems+tutorials to help prepare for this course.  The 
-  * write scientific reports on computational machine learning methodsresults and conclusions.+[[https://www.anaconda.com/distribution/|Anaconda distribution]] is 
 +recommendedwhich is a free download for all platforms. 
 +A quick review of Python will be presented in the first week  
 +of the semester.
  
-For implementations we will be using [[https://www.python.org/|Python]]. You may download and install Python on your computer, and work through the on-line tutorials to help prepare for this course. For the written reports, we will be using [[https://www.latex-project.org/|LaTeX]], a document preparation system, freely available on all platforms. +Class meetings will be a combination of lectures by the instructor and 
- +discussions of your questions.  You are expected to have read the 
-Class meetings will be a combination of lectures by the instructordiscussions of students' questions, and some student presentations in class. +assigned material before each class meeting. All questions are 
- +welcome, no matter how simple you think they are; it is always true 
-A lot of material will be covered in this course. Students are expected to speak up in class with questions and observations they have about the material. Do not expect to be able to complete all assignments working on your own and without asking any questions. If you find yourself wondering what the next step is in finishing an assignment, please feel free to e-mail the instructor. You may also discuss assignments with other students, but your code and report must be written by you+that someone else has a similar question. Do not expect to be able to 
- +complete all assignments working on your own and not asking any 
-You are expected to be familiar with the [[http://www.cs.colostate.edu/advising/student-info.html|CS Department policy]] on cheating and with the [[http://www.cs.colostate.edu/cstop/csdepartment/CodeOfConduct.php|CS Department Code of Conduct]]. This course will adhere to the [[http://www.conflictresolution.colostate.edu/academic-integrity|CSU Academic Integrity Policy]]  and the Student Conduct Code. At a minimum, violations will result in a grading penalty in this course and a report to the Office of Conflict Resolution and Student Conduct Services.+questions. If you find yourself wondering what the next step is in 
 +finishing an assignment, visit or e-mail the instructor or the 
 +graduate teaching assistant. You may also discuss assignments with 
 +other students, but <color red/white>your code must be written by you</color>.  
  
 +You are expected to be familiar with the
 +[[http://www.cs.colostate.edu/advising/student-info.html|CS Department
 +policy on cheating]] and with the
 +[[http://www.cs.colostate.edu/advising/CodeOfConduct.pdf|CS Department
 +Code of Ethics]].  This course will adhere to the CSU Academic
 +Integrity Policy as found in the
 +[[http://www.catalog.colostate.edu/FrontPDF/1.6POLICIES1112f.pdf|General
 +Catalog]] and the
 +[[http://www.conflictresolution.colostate.edu/conduct-code|Student
 +Conduct Code]]. At a minimum, violations will result in a grading
 +penalty in this course and a report to the Office of Conflict
 +Resolution and Student Conduct Services.
  
 ===== Time and Place ===== ===== Time and Place =====
  
-Class meets every Monday, Wednesday and Friday9:00 am 9:50 in Clark Room A103 On-campus and distance-learning students will be able to watch video recordings of lectures.+Class meets every Tuesday and Thursday2:00 PM 3:15 PM, **on-line as 
 +a Microsoft Teams meeting** that you can find [[https://teams.microsoft.com/l/meetup-join/19%3a323d2d59a8f64282b836e440b8cb32d9%40thread.tacv2/1598126257845?context=%7b%22Tid%22%3a%22afb58802-ff7a-4bb1-ab21-367ff2ecfc8b%22%2c%22Oid%22%3a%22bcd6d782-40c2-430e-8091-fd9ebd260de7%22%7d|at this link]].  You may download Microsoft Teams apps for Windows, Mac, and Linux from [[https://docs.microsoft.com/en-us/microsoftteams/get-clients|this link at Microsoft]].
  
 +During the lecture please leave your microphone muted.  if you have a question or comment, feel free to interrupt the lecture by unmuting yourself and saying something like "Excuse me, I have a question" Questions and comments are always welcome!!  I cannot guarantee that I will notice comments that you type in the Chat box.
 ===== Prerequisites ===== ===== Prerequisites =====
  
Line 31: Line 59:
 ===== Textbook ===== ===== Textbook =====
  
-=== Required === +Required[[http://aima.cs.berkeley.edu/|Artificial Intelligence:
- +Modern Approach]], third edition. by 
-[[http://www.cmpe.boun.edu.tr/~ethem/i2ml3e/|Introduction to Machine Learning]], by Ethem Alpaydin, 3rd edition, MIT Press, 2014+[[http://www.cs.berkeley.edu/~russell/|Stuart Russell]] and 
- +[[http://www.norvig.com/|Peter Norvig]].
- +
-=== Optional === +
- +
-On-line material is available on the course [[Resources]] web page.  Other books that may be helpful are listed here. +
- +
-[[http://shop.oreilly.com/product/0636920023784.do|Python for Data Analysis]], by Wes Kinney, O'Reilly Media, Inc., 2013.+
  
-[[http://webdocs.cs.ualberta.ca/~sutton/book/the-book.html| Reinforcement Learning: An Introduction]], by Richard Sutton and Andrew Barto. On-line and free. You can also read the book through Morgan library. Visit [[http://catalog.library.colostate.edu/search~S5?/treinforcement+learning/treinforcement+learning/1%2C12%2C16%2CB/frameset&FF=treinforcement+learning+an+introduction&1%2C%2C3|this page]] and click on the “View electronic book” link. 
  
 ===== Instructors ===== ===== Instructors =====
  
 ^    ^  Office  ^  Hours  ^  Contact  | ^    ^  Office  ^  Hours  ^  Contact  |
-^  [[http://www.cs.colostate.edu/~anderson|Chuck Anderson]]  |  Computer Science Building (CSB) Room 444  |    Monday 1-2, Wednesday 2- |  anderson@cs.colostate.edu\\  970-491-7491 +^  [[http://www.cs.colostate.edu/~anderson|Chuck Anderson]]  |  Computer Science Building\\ Room 444  |  Wednesdays\\ 9 10am\\  [[https://teams.microsoft.com/l/meetup-join/19%3a323d2d59a8f64282b836e440b8cb32d9%40thread.tacv2/1598288070646?context=%7b%22Tid%22%3a%22afb58802-ff7a-4bb1-ab21-367ff2ecfc8b%22%2c%22Oid%22%3a%22bcd6d782-40c2-430e-8091-fd9ebd260de7%22%7d|MS Teams link]]  |  Chuck.Anderson@colostate.edu\\  970-491-7491 
-^  GTA: [[http://www.cs.colostate.edu/~lemin/|Jake Lee]]  |   |  Room 120\\ Wednesday 4 6 PM\\ Friday 2 4 PM  |  lemin@cs.colostate.edu  |+^  GTA:\\  [[https://www.linkedin.com/in/apoorvdp/|Apoorv Pandey]] |    |  Mondays\\ 2:00 - 4:00 PM\\ [[https://teams.microsoft.com/l/meetup-join/19%3a323d2d59a8f64282b836e440b8cb32d9%40thread.tacv2/1598300599034?context=%7b%22Tid%22%3a%22afb58802-ff7a-4bb1-ab21-367ff2ecfc8b%22%2c%22Oid%22%3a%22bcd6d782-40c2-430e-8091-fd9ebd260de7%22%7d|MS Teams Link]]     Apoorv.Pandey@colostate.edu  | 
 +^  GTA:\\   [[https://www.linkedin.com/in/chaitanyaroygaga/|Chaitanya Roygaga]]  |   |  Fridays\\ 2:00 4:00 pm\\ [[https://teams.microsoft.com/l/meetup-join/19%3a323d2d59a8f64282b836e440b8cb32d9%40thread.tacv2/1598301087268?context=%7b%22Tid%22%3a%22afb58802-ff7a-4bb1-ab21-367ff2ecfc8b%22%2c%22Oid%22%3a%22bcd6d782-40c2-430e-8091-fd9ebd260de7%22%7d|MS Teams Link]]  |  Chaitanya.Roygaga@colostate.edu   |
  
  
 ===== Grading ===== ===== Grading =====
  
-Your grade for this course will be based only on the assignments, most of which will require the submission of an ipython notebook that includes text descriptions of your methods, results and conclusions and the python code for defining machine learning algorithms, loading data and applying your algorithms to the data Each notebook will be graded for correct implementation and results, interesting and thorough discussion, and good organization, grammar and spelling.  No quizzes or exams will be given.+Your grade for this course will be based only on six to eight assignments, all 
 +of which will require the submission of a jupyter notebook that 
 +includes python code and and its application to specified problems and data.  In addition, each notebook must include thorough discussions of methods, resultsand conclusions. Each 
 +notebook will be graded for correct implementation and results, 
 +interesting and thorough discussion, and good organization, grammar 
 +and spelling.
  
-We plan for five regular assignments during the semester. In total these will count for 80% of your semester grade. The final assignment is a project designed by you and is worth 20% of your semester gradeThis 20% will be composed of +At the end of the semester, your lowest assignment grade will be dropped,  Your semester grade will be based on the average of your remaining 7 assignment gradesEach assignment will be equally weighted.
-  * 2% for the proposal +
-  * 18% for the written report+
  
-The calculation of the final letter grade will be made as follows:+The calculation of the final letter grade, which will include + and -, 
 +will be based on the standard grading scheme, with A+, A, and A- being 
 +for grades of 90% and above, B+, B, and B- for grades between 80% and 
 +90%, etc.  The minimum grade for each letter grade might be lowered from the standard rubric, 
 +but will not be raised, based on the distribution of semester average 
 +grades for the class.
  
-  * A 90 - 100% +Late assignment solutions will not be accepted, unless you make 
-  * B 80 - 89.9% +arrangements with the instructor at least two days before the due 
-  * C 70 - 79.9% +date.
-  * D 60 - 69.9% +
-  * F below 60%+
  
-These ranges for a letter grade might be shifted a little lower, but will not be raised. 
-Late reports will not be accepted, unless you make arrangements with the instructor at least two days before the due date. 
syllabus.1462381592.txt.gz · Last modified: 2016/05/04 11:06 by anderson